Teaching code

4S009023

Credits

6

Coordinator

Alessandro Farinelli

Language

English

Also offered in courses:

• AI in Robotics of the course Master's degree in Artificial intelligence
• AI in Robotics of the course Master's degree in Artificial intelligence

Scientific Disciplinary Sector (SSD)

INF/01 - INFORMATICS

Courses Single

Authorized

Moodle Seminars 0

The teaching is organized as follows:

Learning objectives

This course presents the main issues related to control and planning techniques for mobile robotic platforms. The objective is to provide the students with the ability to design, apply and evaluate algorithms that allow mobile robotic platforms to interact with the surrounding environment by performing complex tasks with a high level of autonomy. At the end of the course the students must demonstrate to understand the fundamental concepts related to localization, trajectory planning, task planning, decision-making under uncertainty and machine learning in the context of mobile robotic platforms. Moreover, the students must demonstrate to be able to work with the main development tools for mobile robotic applications and to be able to define technical specifications for deigning and integrating software modules for mobile robotic platforms. The students must also be able to deal with professional figures to design solutions for the high level control of mobile robotic platforms and to continue the studies independently following the technical evolution in the field of mobile robotics and developing innovative approaches to improve the state of the art.

To pass the exam, students must demonstrate:
- to have understood the principles behind programming for mobile robots
- to be able to present arguments on the topics of the course in a precise and organic way without digressions
- to know how to apply the acquired knowledge to solve application problems presented in the form of exercises, questions and projects.

Prerequisites and basic notions

No specific requirements.

Program

– Kinematics for mobile robots (e.g., non-holonomic constrain, unicycle-like model).
– Navigation for mobile robots: localization and mapping (e.g., Extended Kalman Filter SLAM), trajectory planning (e.g., navigation functions).
– Decision-making under uncertainty (e.g., Markov Decision Process) .
– Reinforcement learning for mobile robotic platforms (e.g., model-based and model free approaches, Deep RL).
– Lab: implementation of autonomous behaviors for mobile robotic platforms using state of the art development toolkits (e.g., ROS2), simulation environments for empirical evaluation (e.g., Unity), validation on simple mobile platforms (e.g., turtlebot3).

Bibliography

Didactic methods

Lectures in classrooms and in lab with mobile robotic platforms. The slides used during the lessons and other material (eg, access to code and mobile robotic platforms) will be provided.

Learning assessment procedures

The exam consists of an oral test focused on the laboratory activities and a second test that can be chosen between two options: i) a project focused on the implementation of some of the techniques studied during the course; ii) an oral exam focused on the topics studied during the course.

Evaluation criteria

To pass the exam, students must demonstrate:
- to have understood the principles behind programming for mobile robots
- to be able to present arguments on the topics of the course in a precise and organic way without digressions
- to know how to apply the acquired knowledge to solve application problems presented in the form of exercises, questions and projects.

Criteria for the composition of the final grade

The final mark will be obtained from the average of the marks of the two tests.

Exam language

English